{"id":"W2951577137","doi":"10.48550/arxiv.1704.00057","title":"Frames: A Corpus for Adding Memory to Goal-Oriented Dialogue Systems","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Task (project management); Baseline (sea); Frame (networking); Presentation (obstetrics); Tracking (education); Artificial intelligence; Natural language processing; State (computer science); Human–computer interaction; Programming language; Psychology; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001967777,0.001743946,0.0007948978,0.004828051,0.002055272,0.001796899,0.00202194,0.002540779,0.0112946],"category_scores_gemma":[0.01359293,0.0005619896,0.0009423255,0.003523522,0.0009982616,0.002187708,0.002918512,0.001692551,0.008204388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001422619,"about_ca_system_score_gemma":0.001523947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01421638,"about_ca_topic_score_gemma":0.02836593,"domain_scores_codex":[0.9962962,0.001599949,0.0003901627,0.0008903616,0.0005904793,0.0002328067],"domain_scores_gemma":[0.9927786,0.003890387,0.0004722099,0.001180822,0.001208792,0.0004691535],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001684887,0.0009174786,0.01195303,0.005767051,0.0003844569,0.001331619,0.00690545,0.007701338,0.01430817,0.01346226,0.7433099,0.1922743],"study_design_scores_gemma":[0.0005996924,0.0004078038,0.04787855,0.0008667906,0.0002004972,0.001287463,0.004368755,0.02617499,0.01167391,0.01363732,0.8925977,0.0003066798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.1458704,0.01008012,0.05009419,0.001938937,0.001812941,0.001670316,0.745741,0.01202681,0.03076536],"genre_scores_gemma":[0.1531292,0.001074488,0.04595461,0.0003774182,0.0003407469,0.002535656,0.7880647,0.001115616,0.007407549],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01421638,"threshold_uncertainty_score":0.03778422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06518538499493316,"score_gpt":0.2105848772668836,"score_spread":0.1453994922719504,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}